人工智能辅助下的心理健康新型测评

近年来,人工智能技术的飞速发展及应用催生了"智能化心理健康测评"这一领域。智能化心理健康测评能够弥补传统方法的不足,降低漏诊率并提高诊断效率,这对于心理健康问题的普查及预警具有重大意义。目前,智能化心理健康测评处于初步发展阶段,研究者基于在线行为数据、便携式设备数据等开展主要以数据驱动为导向的探索研究,旨在实现更高的预测准确率,但是测评结果的可解释性等指标尚不够理想。未来的智能化心理健康测评需要强调心理学领域知识和经验的深度介入,提高测评的针对性和精细化程度,加强信效度检验,这对于智能化心理健康测评工具的进一步发展和应用至关重要。     

环境公正:和谐社会的基本前提

人与人的和谐是和谐社会的“底线要求”,人与社会的和谐是和谐社会的核心所在,而人与自然的和谐是和谐社会的基本前提。人与自然和谐集中体现为环境公正。它首先是指人与自然物种之间的种际公正,具体体现为两个维度的公正：在空间维度上,要促进国际公正、族际公正、域际公正、群际公正;在时间维度上具有代际公正意识。     

Classifying simulated air threats with fast and frugal heuristics

In three experiments, subjects learned to classify simulated aircraft using four probabilistic cues then classified test sets designed to contrast predictions of several compensatory and non-compensatory heuristics. Results indicated that a proportion of subjects appeared to use a non-compensatory fast and frugal heuristic but that significant proportions used less frugal compensatory decision rules. The relative proportions of subjects exhibiting responses consistent with the fast and frugal heuristic versus other decision rules was largely unaffected by manipulations of time pressure and perceived cue uncertainty. An extreme time constraint, however, did result in significant differences in the proportions of subjects who preferred non-compensatory to compensatory decision rules. These results suggest that it is possible to model multi-attribute decision tasks like threat assessment with a fast and frugal heuristic although no single heuristic is a general model for the simulated threat assessment task. Copyright © 2006 Crown in the right of Canada. Published by John Wiley & Sons, Ltd.     

The fast and the female: Gender differences in wellbeing and wage consequences of commute impedance

At equal distance, the impedance created by traffic congestion strongly affects the duration of commute. Extant literature indicates that commute impedance negatively affects wellbeing, distinctly from the distance and the duration of commute. These negative effects are reported to be larger for women. Consequently, workers, especially females, must be willing to accept lower wages if reaching the job location entails fewer traffic congestions and accommodates a speedier commute. Using the Canadian General Social Survey of 2015 and the Census of 2016, the present paper assesses the wellbeing and wage consequences of commute impedance on men and women who drive to work. The study first demonstrates that the negative impact of commute impedance on wellbeing is greater for women. Second, consistent with the greater negative effect of traffic congestion on their wellbeing, women appear to pay a price off their wages, in order to avoid commute impedance. The policy implications are discussed.     

Inferring task performance and confidence from displays of eye movements

Eye movements reveal what is at the center of people's attention, which is assumed to coincide with what they are thinking about. Eye-movement displays (visualizations of a person's fixations superimposed onto the stimulus, for example, as dots or circles) might provide useful information for diagnosing that person's performance. However, making inferences about a person's task performance based on eye-movement displays requires substantial interpretation. Using graph-comprehension tasks, we investigated to what extent observers (N = 46) could make accurate inferences about a performer's multiple-choice task performance (i.e., chosen answer), confidence, and competence from displays of that person's eye movements. Observers' accuracy when judging which answer the performer chose was above chance level and was higher for displays reflecting confident performance. Observers were also able to infer performers' confidence from the eye-movement displays; moreover, their own task performance and perceived similarity with the performer affected their judgments of the other's competence.     

Assessing the process of desensitization therapy: Five practical measures

Assessment of phobic behavior has included self-report, physiological, and in vivobehavioral measures. While self-report measures are convenient, they suffer from subject bias and a low predictive validity. Physiological and in vivobehavioral measures are often too cumbersome to implement in standard clinical practice. The current study investigated the validity of five convenient measures of phobic behavior during the process of desensitization therapy. Responses of 14 clinically phobic patients were compared on phobic and neutral scenes presented within the context of systematic desensitization therapy. Phobic scenes resulted in less clarity of scene visualization, a longer latency to clear scene visualization, higher subjective units of discomfort (SUDs) at clear visualization, a longer latency to relaxation, and higher SUDs at relaxation. The measures seemed to reflect accurately the process and stages of desensitization therapy and showed low to high intercorrelations. The pragmatic value of these measures is discussed, as well as suggestions for future validational research.     

Racial bias in behavioral assessment of children's social skills

The social skills of 20 second- and sixth-grade students were assessed by 20 trained raters using the Social Skills Test for Children (SST-C). Rater and child characteristics were examined to determine whether differences in social skills ratings were due to the race of the rater or the race of the children being rated or due to the interactive effects of these characteristics, which would suggest racial bias in the ratings procedure. The results showed that the race of the rater did affect some behavioral observations. Black raters gave higher scores than white raters on four behavioral categories: response latency, appropriate assertion, effective assertion, and smiling. White raters gave higher scores for head position and gestures. The results of this study replicated earlier findings of significant differences in social skills ratings due to the race and age of the child being rated. The results also showed modest racial bias effects in that black and white raters scored black and white children differentially on two behavioral categories: overall skill ratings and smiling. These results suggested that most behavioral categories of the SST-C were not systematically affected by racial bias. However, the most subjective rating, overall skill, did evidence racial bias effects. This finding is consistent with previous data showing that subjective ratings may be most affected by racial bias.